Spaces:
Running
Running
| title: README | |
| emoji: 🍎 | |
| colorFrom: gray | |
| colorTo: blue | |
| sdk: static | |
| pinned: false | |
| # NetProjects | |
| **Open models, ready to run on Apple Silicon.** | |
| We convert and test open models for [MLX](https://github.com/ml-explore/mlx), | |
| so they run locally on a Mac with no cloud and no API keys. We check every | |
| build against the original model before it goes up, and we publish speed | |
| numbers from real hardware (MacBook Pro M5 Max, 128 GB). | |
| ## Models | |
| | Family | Builds | What it's for | | |
| |---|---|---| | |
| | **H2O-Lightning 4B** | [q8](https://huggingface.co/netprojects/h2o-lightning-4b-mlx-q8) · [q4](https://huggingface.co/netprojects/h2o-lightning-4b-mlx-q4) | Small vision-language model from H2O.ai; reads documents and images | | |
| | **IBM Granite Switch 4.1** | 8B [8-bit](https://huggingface.co/netprojects/granite-switch-4.1-8b-mlx-8bit) · [4-bit](https://huggingface.co/netprojects/granite-switch-4.1-8b-mlx-4bit) — 30B [8-bit](https://huggingface.co/netprojects/granite-switch-4.1-30b-mlx-8bit) · [4-bit](https://huggingface.co/netprojects/granite-switch-4.1-30b-mlx-4bit) | IBM Granite with switchable chat, decision and guardian modes | | |
| | **NVIDIA Nemotron Dory 1.0 4B** | [8-bit](https://huggingface.co/netprojects/nemotron-dory1.0-4b-mlx-8bit) · [bf16](https://huggingface.co/netprojects/nemotron-dory1.0-4b-mlx-bf16) | Compact NVIDIA-based model for fast local use | | |
| | **AutoTrust JEV 35B** | [8-bit](https://huggingface.co/netprojects/JEV-35B-mlx-8bit) · [4-bit mixed](https://huggingface.co/netprojects/JEV-35B-mlx-4bit-mixed) · [3-bit mixed](https://huggingface.co/netprojects/JEV-35B-mlx-3bit-mixed) | AutoTrust decision and classification model | | |
| | **AutoTrust JEV 27B v1.1** | [8-bit](https://huggingface.co/netprojects/AutoTrust-JEV-27B-v1.1-mlx-8bit) · [4-bit](https://huggingface.co/netprojects/AutoTrust-JEV-27B-v1.1-mlx-4bit) | Decision model with bidirectional prompt reading (custom loader included) | | |
| ## How we build | |
| - Conversions use the standard `mlx-lm` / `mlx-vlm` tools; where a model | |
| needs custom code, the loader is open source on GitHub. | |
| - Each card says which upstream revision it was built from, how it was | |
| quantized and how it was checked, with speed and memory measured on an M5 Max. | |
| - Licences follow the original model. | |
| ## Code | |
| - [h2o-lightning-mlx](https://github.com/internet-projects/h2o-lightning-mlx) | |
| - [granite-switch-mlx](https://github.com/internet-projects/granite-switch-mlx) | |
| ## Also | |
| We also work on small calibrated decision models, fact-checking and | |
| content quality for long-running websites, and open-source tooling | |
| for small teams. | |
| Spotted a problem or want a model converted? Open a discussion on any model page. |